@matiaslapolla· 4h
Documented LLM parameter timing for local model optimization
dev
Back after 6 days
Welcome back
170.3ktokens
6prompts
1:10:02time
17lines
Claude Codeclaude-opus-5[1m]Markdown$2.95
Documented the distinction between load-time and inference-time LLM parameters for local model serving.
Tokens / prompt28.4k
Cost / line$0.173
Cache hit95%
Burn rate$2.53/hr
Derived from this session's token and cost data. Not shown on the feed.
Comments